add parse xlsx

main.py

+import copy
+import re
+import json
+import pandas as pd
+import requests
+
+url = "http://172.18.137.46:9211/liexin_all_sku/_search"
+
+goods_name = "BNC/SMA-JJ"
+
+query = {
+    "_source": ["goods_id", "goods_name", "brand_name"],
+    "query": {
+        "bool": {
+            "must": [
+                {
+                    "match": {
+                        "goods_name": goods_name
+                    }
+                },
+                {
+                    "term": {
+                        "goods_status": 1
+                    }
+                },
+                {
+                    "term": {
+                        "forbid_status": 0
+                    }
+                },
+                {
+                    "range": {
+                        "stock": {
+                            "gte": 0
+                        }
+                    }
+                }
+            ]
+        }
+    }
+}
+
+black_list = {"eastsheep", "ABB", "BRsanyuan", "JCSTRONG", "TECHNOLOGY",
+              "OMRON", "Schneider", "Electric", "ZWZDH", "GKNC",
+              "ALINX", "DELL", "ANALOG", "DEVICES", "LR-LINK", "molex", "NVIDIA"
+                                                                        "Xilinx", "Anybus", "FTDEVICE", "JZLDP",
+              "LunderwaterH", "PANT",
+              "TRANSCELL", "unistrong", "VOLTCEL", "FULANGDE", "CNC", "AMD", "TEJIATE",
+              "ChangHong", "ABI", "USB", "BEICHEN", "HuiKong", "JKJI", "LONCONT", "WEKDK", "JUWEIDE",
+              "ZKE", "AZBIL", "CDOE", "DLEN", "GDSW", "Pilz", "HONEYWELL", "QMA", "SANGFOR", "SKINHEAD",
+              "HITTERY", "TURCK", "WAGO", "Xilinx", "EMA", "ZLG", "LEFILTER", "BIAO", "FENG", "CDIY",
+              "CPC", "HW", "Gjqs", "SZCOMARK", "tyuhk", "ERIKOLE", "LZALY", "LZQLY", "SIEMENS", "0.8mm", "100G", "11p",
+              "12p", "16mm", "2.4G", "3.7v", "905nm", "DIEWU", "EB-LINK", "SUNON", "TEXAS", "XINQY", "LOBOROBOT", "H3C",
+              "EB-LINK", "cutersre", "HEMEI", "HRE", "ZHSY", "kankeirr", "21KE", "RITAR", "AERFID", "KEDACOM", "KSD",
+              "NEWSTARTOS", "TADIRAN", "FENGYINGZI", "ADI", "BOURNS", "COMFAST", "Continental", "CTS", "CYPRESS",
+              "DIODES",
+              "Mosfet", "ECS", "ERNI", "ERNI", "HIK", "HOTTECH", "HUASHUO", "INFINEON", "Infineon", "INFINEON", "INTEL",
+              "Isabellenhuette", "KAMAYA", "Knowles", "KOA", "KYOCERA", "MAXIM", "MDD", "Microchip", "Mini-Circuits",
+              "Murata", "NEXPERIA", "Nichicon", "NXP", "Panasonic", "PEM", "ROHM", "ROQANG", "Semitec", "SILERGY",
+              "SXN",
+              "TDK", "THine", "CAN", "TOSHIBA", "UMW", "UniOhm", "VISHAY", "Vox", "Power", "YANGJIE", "youyeetoo",
+              "Chian-Chia", "CCO", "COILCRAFT", "ZHOUZHI", "Arty", "Xilinx", "Sipeed", "Tang", "Primer",
+              "WENHAOYONGSHUN",
+              "Infineon", "SILICON", "Arduino", "BINJIASHENG", "cjiang", "Continental", "CrossChip", "DIODES",
+              "GOOD-ARK",
+              "GWINSTEK", "HGSEMI", "HOTA", "HGSEMI", "INFINEON", "Knowles", "Littelfuse", "MCC",
+              "muRata", "Nexperia", "ONSEMI", "PSA", "Slkor", "UTC", "YAGEO", "YLPTEC", "ASUNDAR", "BOSENDE", "HGSEMI",
+              "YXC", "INFINEON", "FANUC", "HMILU", "Sinexcel", "SONY", "ALINX", "BEICHEN", "EAO", "TaoTimeClub",
+              "KONNAD", "Tenda", "Kingston", "LEACH", "Multilane", "10dB", "20dB", "18GHz", "3dB", "Gratool",
+              "HIKVISION",
+              "UGREEN", "xiaovv", "maxhub", "SAMSUNG", "SAMZHE", "ALINX", "Xilinx", "Lenovo", "MeeTap", "BCNET",
+              "LANGQING",
+              "ORICO", "HUB", "Panasonic", "SDKELI", "10m", "9m", "8m", "7m", "6m", "5m", "4m", "3m", "2m", "1m"
+              }
+count = 0
+
+
+def main():
+    df = pd.read_excel('table.xlsx')
+    data = df.iloc[:, [0]].values
+    ans = []
+    for i in range(len(data)):
+        sku_name_str = data[i][0]
+        res_tmp = match_sku(sku_name_str)
+        ans.append(res_tmp)
+
+    for i in range(len(ans)):
+        for j in range(len(ans[i])):
+            tmp_goods_name = ans[i][j]
+            tmp_query = query
+            tmp_query["query"]["bool"]["must"][0]["match"]["goods_name"] = tmp_goods_name
+
+
+def match_sku(s: str) -> []:
+    # s = "RG58/U射频连接线SMA公头转BNC公头延长线 SMA/BNC-JJ Q9/SMA-JJ RG58/U-SMA/BNC-JJ 2m"
+    res = []
+    arr = s.split(" ")
+    for i in range(len(arr)):
+        tmp = arr[i].strip(" ")
+        if len(tmp) == 0 or tmp in black_list:
+            continue
+        # 正则表达式检测被空格分开的每个字符串，每个字符串 最多检测三个 英文字母，"/", "-", 数字0-9组成的子字符串
+        pattern = re.compile(
+            r'[^0-9a-zA-Z]*([0-9a-zA-Z][0-9a-zA-Z/-]{2,})[^0-9a-zA-Z/-]*([0-9a-zA-Z][0-9a-zA-Z/-]{2,})*[^0-9a-zA-Z]*([0-9a-zA-Z][0-9a-zA-Z/-]{2,})*')
+        m = pattern.match(tmp)
+        if m is not None:
+            for k in range(len(m.groups())):
+                tmp_str = m.groups()[k]
+                if tmp_str is not None:
+                    # 黑名单中的不会加入结果列表
+                    if tmp_str in black_list:
+                        continue
+                    # 检查是否为纯数字，纯数字不会加入结果列表
+                    rex = re.compile("^[0-9]*$")
+                    mat = rex.search(tmp_str)
+                    if mat is not None:
+                        continue
+                    res.append(tmp_str)
+    return res
+
+
+def post_to_elasticsearch(q: dict):
+    response = requests.post(url=url, data=json.dumps(q), headers={"Content-Type": "application/json"})
+    ans = response.json()
+    return ans
+
+
+if __name__ == '__main__':
+    main()